# High precision grasp pose detection in dense clutter

arXiv: https://arxiv.org/abs/1603.01564 · HTML: https://mlsanity.com/paper/1603.01564/

## Key facts

- Cited by 34 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 4 Mar 2016.

## Built on by (most cited first, 30 of 34)

- [Synergies Between Affordance and Geometry: 6-DoF Grasp Detection via Implicit Representations](https://mlsanity.com/paper/2104.01542/) (2021)
- [Scalable Scene Flow from Point Clouds in the Real World](https://mlsanity.com/paper/2103.01306/) (2021)
- [GraspSplats: Efficient Manipulation with 3D Feature Splatting](https://mlsanity.com/paper/2409.02084/) (2024)
- [Long-Horizon Manipulation of Unknown Objects via Task and Motion Planning with Estimated Affordances](https://mlsanity.com/paper/2108.04145/) (2021)
- [Edge Grasp Network: A Graph-Based SE(3)-invariant Approach to Grasp Detection](https://mlsanity.com/paper/2211.00191/) (2022)
- [A3VLM: Actionable Articulation-Aware Vision Language Model](https://mlsanity.com/paper/2406.07549/) (2024)
- [DDGC: Generative Deep Dexterous Grasping in Clutter](https://mlsanity.com/paper/2103.04783/) (2021)
- [Learning High-DOF Reaching-and-Grasping via Dynamic Representation of Gripper-Object Interaction](https://mlsanity.com/paper/2204.13998/) (2022)
- [An Economic Framework for 6-DoF Grasp Detection](https://mlsanity.com/paper/2407.08366/) (2024)
- [Composing Pick-and-Place Tasks By Grounding Language](https://mlsanity.com/paper/2102.08094/) (2021)
- [ICGNet: A Unified Approach for Instance-Centric Grasping](https://mlsanity.com/paper/2401.09939/) (2024)
- [Simultaneous Semantic and Collision Learning for 6-DoF Grasp Pose Estimation](https://mlsanity.com/paper/2108.02425/) (2021)
- [Detect Everything with Few Examples](https://mlsanity.com/paper/2309.12969/) (2023)
- [Collision-Aware Target-Driven Object Grasping in Constrained Environments](https://mlsanity.com/paper/2104.00776/) (2021)
- [REGRAD: A Large-Scale Relational Grasp Dataset for Safe and Object-Specific Robotic Grasping in Clutter](https://mlsanity.com/paper/2104.14118/) (2021)
- [Simultaneous Multi-View Object Recognition and Grasping in Open-Ended Domains](https://mlsanity.com/paper/2106.01866/) (2021)
- [GKNet: grasp keypoint network for grasp candidates detection](https://mlsanity.com/paper/2106.08497/) (2021)
- [Scene Editing as Teleoperation: A Case Study in 6DoF Kit Assembly](https://mlsanity.com/paper/2110.04450/) (2021)
- [Learning Any-View 6DoF Robotic Grasping in Cluttered Scenes via Neural Surface Rendering](https://mlsanity.com/paper/2306.07392/) (2023)
- [Visionary: Vision architecture discovery for robot learning](https://mlsanity.com/paper/2103.14633/) (2021)
- [Bootstrapping Motor Skill Learning with Motion Planning](https://mlsanity.com/paper/2101.04736/) (2021)
- [GASCN: Graph Attention Shape Completion Network](https://mlsanity.com/paper/2201.07937/) (2022)
- [Bimanual Grasp Synthesis for Dexterous Robot Hands](https://mlsanity.com/paper/2411.15903/) (2024)
- [Integration of Vision-based Object Detection and Grasping for Articulated Manipulator in Lunar Conditions](https://mlsanity.com/paper/2309.01055/) (2023)
- [Joint Flow Trajectory Optimization For Feasible Robot Motion Generation from Video Demonstrations](https://mlsanity.com/paper/2509.20703/) (2025)
- [Data-efficient learning of object-centric grasp preferences](https://mlsanity.com/paper/2203.00384/) (2022)
- [Language-Guided Object Search in Agricultural Environments](https://mlsanity.com/paper/2503.01068/) (2025)
- [Grasp the Graph (GtG) 2.0: Ensemble of Graph Neural Networks for High-Precision Grasp Pose Detection in Clutter](https://mlsanity.com/paper/2505.02664/) (2025)
- [Sim-MEES: Modular End-Effector System Grasping Dataset for Mobile Manipulators in Cluttered Environments](https://mlsanity.com/paper/2305.10580/) (2023)
- [Robust Loss Functions for Object Grasping under Limited Ground Truth](https://mlsanity.com/paper/2409.05742/) (2024)

## Abstract (arXiv)

This paper considers the problem of grasp pose detection in point clouds. We follow a general algorithmic structure that first generates a large set of 6-DOF grasp candidates and then classifies each of them as a good or a bad grasp. Our focus in this paper is on improving the second step by using depth sensor scans from large online datasets to train a convolutional neural network. We propose two new representations of grasp candidates, and we quantify the effect of using prior knowledge of two forms: instance or category knowledge of the object to be grasped, and pretraining the network on simulated depth data obtained from idealized CAD models. Our analysis shows that a more informative grasp candidate representation as well as pretraining and prior knowledge significantly improve grasp detection. We evaluate our approach on a Baxter Research Robot and demonstrate an average grasp success rate of 93% in dense clutter. This is a 20% improvement compared to our prior work.